College Website Chatbot – a bot can create a bond

A Mini project report submitted in partial fulfilment of the requirement

for the award of degree of

BACHELOR OF TECHNOLOGY

COMPUTER SCIENCE AND ENGINEERING

Submitted by
P S GURUNADH N ABHISHEK
(18341A0598) (18341A0591)

P GIRISH K SRUJITHA
(18341A05A4) (18341A0562)

Under the esteemed guidance of

MR P SRINIVASA RAO
Assistant Professor, Dept. of CSE

GMR Institute of Technology

An Autonomous Institute Affiliated to JNTUK, Kakinada
(Accredited by NBA, NAAC with ‘A’ Grade & ISO 9001:2008 Certified Institution)

GMR Nagar, Rajam – 532127,

Andhra Pradesh, India
August 2021
 Department of Computer Science and Engineering

CERTIFICATE

This is to certify that the Mini Project entitled “COLLEGE WEBSITE CHATBOT – A BOT CAN

CREATE A BOND” submitted by P S Gurunadh (18341A0598), N Abhishek(18341A0591), P Girish

(18341A05A4), K Srujitha (18341A0562) has been carried out in partial fulfilment of the requirement for

the award of degree of Bachelor of Technology in Computer Science and Engineering of GMRIT,

Rajam affiliated to JNTUK, KAKINADA is a record of bonafide work carried out by them under my

guidance & supervision. The results embodied in this report have not been submitted to any other University

or Institute for the award of any degree.

Signature of the Supervisor Signature of the H.O.D

Mr. P Srinivasa Rao Dr. A V Ramana
Assistant Professor Professor and Head
Department of CSE Department of CSE
GMRIT, Rajam. GMRIT, Rajam.
 ACKNOWLEDGEMENT

It gives us an immense pleasure to express deep sense of gratitude to our guide, Mr. P
Srinivasa Rao, Assistant Professor, Department of Computer Science and Engineering of whole hearted
and invaluable guidance throughout the report. Without his sustained and sincere effort, this report would
not have taken this shape. He encouraged and helped us to overcome various difficulties that we have faced
at various stages of our report.

We would like to sincerely thank Dr. A V Ramana, Professor & HOD, Department of
Computer Science and Engineering, for providing all the necessary facilities that led to the successful
completion of our report.

We take privilege to thank our Principal Dr. C.L.V.R.S.V.Prasad & Director Education Dr.
J. Girish, who has made the atmosphere so easy to work. We shall always be indebted to them.

We would like to thank all the faculty members of the Department of Computer Science and
Engineering for their direct or indirect support and also all the lab technicians for their valuable suggestions
and providing excellent opportunities in completion of this report.

P S Gurunadh(18341A0598)
N Abhishek(18341A0591)
P Girish(18341A05A4)
K Srujitha(18341A0562)
 ABSTRACT
Technology is growing exponentially in this modern world. Machine Learning(ML) and Artificial
Intelligence(AI) are playing a key role in a wide range of critical applications. The evolving AI applications
are super smart and highly cognitive. In particular, advances in natural language processing enable a new
way of interaction that accelerates insight from existing information sources, thereby contributing to the
process of learning. In such application, normal bots are impressive for conversation. This project is
intended to create a chatbot to be used by students to get their queries responded easily from the college
website. This chatbot has the capacity to make friendly conversations and respond to the queries. Moreover,
it provides information with faculty directory, upcoming events, college achievements and many more. Most
of the existing chatbots lack cognitive thinking and fail to accommodate anything that is off the script. In
order to address these problems, this chatbot extends the implementation of the current chatbots by adding
sentiment analysis and active learning. Although, this bot does not correctly recognize the user's query as
positive, negative and neutral, the system was partially successful in adding empathy to the chatbot. To
handle all queries we need to train the data rigorously, which are off-script.
 TABLE OF CONTENTS

ACKNOWLEDGEMENT I

ABSTRACT II

1.INTRODUCTION 7

2.LITERATURE REVIEW 11

3.SYSTEM DESIGN 12

4.IMPLEMENTATION 14

5.OUTPUT 17

6.RESULTS & DISCUSSION 18

7.SOURCE CODE

8.CONCLUSION 19

9.REFERENCES 20
 TABLE OF FIGURES

1. Fig1 Graph 7

2. Fig2 Usecase diagram 12

3. Fig3 Activity diagram 13

4. Fig4 Output1 10

5. Fig5 Output2 11
 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



1. INTRODUCTION
The field of artificial intelligence (AI) has shown an upward trend of growth in the 21st century
(from 2000 to 2015). The evolution in AI has advanced the development of human society in our own time,
with dramatic revolutions shaped by both theories and techniques. However, the multidisciplinary and fast
growing features make AI a field in which it is difficult to be well understood. Throughout the development
of AI, such as machine learning techniques shift, it has resulted in the explosion of publications and given
birth to some sub-fields. we can see that the number of AI papers has been increasing roughly linearly in
the 21st Century.

Chat bot is one of the Artificial intelligence features that can be embedded and used through any major
message applications.

Fig1: Graph

Applications of Artificial intelligence:

Real life examples of AI are:

Self-Driving Cars

Boston Dynamics

Navigation Systems

Chatbots

Benefits of AI:
The most important purpose of A.I. is to reduce human causalities in

• Wars

• Dangerous Workspaces

Dept of CSE, GMRIT Page 7

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



• Car Accidents

• Natural Disasters

Or to just make everybody life easier by helping with tasks such as

• Cleaning

• Shopping

• Transportation

For these general helps, there are so many ways and chat bot are one of them. In our project we are
developing a chat bot application which is interlinked with the student details, where a student can have a
informational conversation with developed chat bot by using Natural Language Processing .

Intelligent Chatbot is a project that explores what can be accomplished with AI agents in the world we
live in today. Alan Turing (1912-1954), known as the father of modern computing, developed the idea of
artificial intelligence. Perhaps most famously known for breaking the Enigma code used by the Germans in
WWII, which was widely regarded as unbreakable, he lay the foundations for the development of computer
science explored what is possible using electronic computers and artificial intelligence. In his 1950 paper
on Computing Machinery and Intelligence, he asks the question; “Can machines think?”. He created a test,
with the fitting name of the Turing test, whereby a machine is tested on its ability to exhibit intelligent
behavior equivalent to, or indistinguishable from, that of a human. Throughout the paper he delves deeper
into this idea and I came across an interesting quote. To quote directly from Turing, “I believe that in about
fifty years‟ time it will be possible to programmed computers, with a storage capacity of about 109, to make
them play the imitation game so well that an average interrogator will not have more than 70 per cent chance
of making the right identification after five minutes of questioning. He wasn’t too far off. In June 2014, a
computer program called Eugene, which simulated a 13- year-old Ukrainian boy was said to have
successfully passed the Turing test at an event held at Reading University’s School of Systems Engineering.
Some artificial intelligence experts refuse to recognize this as a legitimate victory but it is interesting to note
how close Turing’s prediction was ]Messaging applications are the #1 most used applications in the world
at the moment and some businesses are already taking advantage of this and developing chatbots of their
own to complement their social media presence. With messaging applications taking up the majority of a
user’s time, it makes sense for businesses to capitalize on this.

Dept of CSE, GMRIT Page 8

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



Bots are becoming smarter and faster and will soon become easier to use than a website or app. A
recent inquiry into the area of chatbots indicated that 180 bot-related 7 companies have attracted $24 billion
in funding towards the development of AI driven bot applications. Microsoft CEO Satya Nadella was quoted
saying “Bots are the new apps”, with Microsoft set on exploring deeper into the world of chatbots and
accelerating the innovation and sophistication of chatbots, I have found this project both interesting and
exciting as I dived into Microsoft newest platform; Microsoft Bot Framework. With many companies
already creating their own bots using the Bot Framework such as eBay, Skyscanner, StubHub and
Foursquare, I believe that in the next few years every major business will have a chatbot to deal with
customers „basic queries and maybe even go as far as processing full orders. Chatbots have the potential to
replace call centers, customers can get their queries answered simply by opening their favorite messaging
platform and chatting with a bot.

PROBLEM STATEMENT:
Creating a college chatbot is our main aim. Chat bot need to interact with the user through text, it
means it should take as text input and provide the validate response in the form of text. Chat bot need to
satisfy the all the queries related to student details and make the user satisfied. Chatbot should start the
conversation and it should continue the conversation until the user want to end the conversation.

EXISTING SYSTEM:
Many colleges of India doesn’t have any chatbot service systems, The Communication between the
officials and customer is done through either customer agent service through call or email or offline services
which lead to delayed responses. Sometimes the queries or doubts may overlap or miss, therefore customer
need to wait for long time, assuming that he may get response from officials soon. Some question or doubts
are very awkward that may irritate the officials to answer the same question again and again.

PROPOSED SYSTEM:
In this project we are developing a chatbot where speech text to text communication between the
chat bot and human is possible. This Application Bot which act as a customer support agent between student
and college Officials. This Bot is tries to answer all the queries related to the college details up to its
knowledge (the knowledge depends on its training).

ADVANTAGES OF PROPOSED SYSTEM:

• The main advantage of chatbot is that the human interference will be reduced.

Dept of CSE, GMRIT Page 9

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



• Agent will be available in 24/7 working hours. Accessible any time.

• Machine will never go into irritated mode for the quires.

• Cost is effective

Dept of CSE, GMRIT Page 10

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



2. LITERATURE REVIEW

According to the “D. Carlander Reuterfelt, A. Carrera, C. A. Iglesias, O. Araque, J. F. Sánchez

Rada and S. Muñoz” [1] Super-Agent(chatbot Name), a modular cognitive agent architecture for
pedagogical question answering, featuring social dialogue (small talk), improved for a specific knowledge
domain and is to provide insights and solve doubts about Data Science.

According to the “Boris Galitsky ,Dmitry Ilvovsky" [2] the chat bot is designed as an automated
customer support or assisting a user in learning product features, product usability, suitability,
troubleshooting and other related tasks. They used disclosed tree by DT parsers to combine paragraphs of
documents which is a basis for interactive content exploration facilitated by the chat bot.

According to the “G. Daniel, J. Cabot, L. Deruelle and M. Derras” [3] a multi-channel and
multiplatform chatbot modeling framework and an increase in the reusability of the chatbot and facilitates
its redeployment when the needs of the company change, including the possibility of evolving the NLU
engine used during the text analysis phase.

According to the “E. H. Wu, C. Lin, Y. Ou, C. Liu, W. Wang and C. Chao” [4] evaluation on how
well current chatbot technologies assist users learning on E-Learning platforms and how these technologies
could possibly reduce problems such as feelings of isolation and detachment is discussed.

According to the “Lei Cui, Shaohan Huang, Furu Wei, Chuanqi Tan, Chaoqun Duan, and Ming
Zhou” [5] an overview of cloud-based chatbots technologies along with programming of chatbots and
challenges of programming in current and future Era of chatbot, the drawback in the design and development
of these chatbots is also discussed.

According to the “L. Zhang, Y. Yang, J. Zhou, C. Chen and L. He” [6] a retrieval-polished (RP)
model for response generation that polishes a draft response based on a retrieved prototype and a generation-
based polisher is designed to obtain a polished response.

Dept of CSE, GMRIT Page 11

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



3. SYSTEM DESIGN
UML DIAGRAMS

Use case Diagram:

A use case is a list of steps, typically defining interactions between a role (known in Unified
Modeling Language (UML) as an "actor" and a system, to achieve a goal. The actor can be a human, an
external system, or time.

Use case diagram commonly contains

·Use cases

·Actors

·Dependency generalization and association relationships

Scenario: In this scenario, the citizen has only two functions i.e. to open the chat bot and to ask the query.
The Chat-bot has few operations namely to search the response, reply for the query asked by the user,
search for the results.

Fig2: Use case diagram

Dept of CSE, GMRIT Page 12

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



Activity Diagram:
Activity diagrams are graphical representations of workflows of stepwise activities and actions
with support for choice, iteration and concurrency. In the Unified Modeling Language, activity diagrams
are intended to model both computational and organizational processes.

Scenario: In this scenario, initially the user enters the query. Chat bot checks the context to the given query.
If it is out of context then it simply ends the conversation or else it tries to match in the intents and entities.
After checking through the intents it generates the response. In last it performs the action in text based or
voice based.

Fig3: Activity Diagram

Dept of CSE, GMRIT Page 13

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



4. IMPLEMENTATION

In this implementation phase we have divided our task into certain sub modules that make us easy to build
our project. Those sub modules are again sub divided into sub modules
• Creating question and answers in a JSON file

o Creating Intents

o Tags

o Patterns

o Responses

• Tokenization & Lemmitization

• Model Creation
• Integration with Web Browser
• Deploying via tkinter

Creating JSON file

As we know the main point of chatbot is to answer for the specified questions of that particular field say,
education, health, corporate etc…, For this reason we need a question set in which queries are exclusively
on college website. These questions may be of regarding exams, attendance, faculty details, major
upcoming events, rankings and so on. Following is the JSON file created for this project.

intents.json:

Sample intent

{"intents": [
{"tag": "greeting",
"patterns”:["Hi there", "How are you", "Is anyone
there?","Hey","Hola", "Hello", "Good day"],
"responses”:["Hello, thanks for asking", "Good to see you again",
"Hi there, how can I help?"],
"context": [""]}]}

Dept of CSE, GMRIT Page 14

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



Tokenization & Lemmitization

Tokenization is the process of tokenizing or splitting a string, text into a list of tokens. One can think of
token as parts like a word is a token in a sentence, and a sentence is a token in a paragraph.

Lemmatization is the process of grouping together the different inflected forms of a word so they can be
analyzed as a single item. Lemmatization is similar to stemming but it brings context to the words. So it
links words with similar meaning to one word.

Sample Code:

import nltk
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
Patterns in the JSON file gets tokenized by below code snippet
w = nltk.word_tokenize(pattern)
Now these words gets lemmitized so that duplicates were removed
words = [lemmatizer.lemmatize(w.lower()) for w in words if w not in
ignore_words]

Model Creation

After lemmitization is done, it is time to create model. Here we divide data into train and test set. After that
a model, especially a 3-layer model is created with first layer comprises of 128 neurons, second layer with
64 neurons, 3rd output layer contains number of neurons equal to number of intents to predict output intent.

Sample Code:

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout
from keras.optimizers import SGD

Dept of CSE, GMRIT Page 15

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



Deployment via tkinter GUI

Python offers multiple options for developing GUI (Graphical User Interface). Out of all the GUI methods,
tkinter is the most commonly used method. It is a standard Python interface to the Tk GUI toolkit shipped
with Python. Python with tkinter is the fastest and easiest way to create the GUI applications. Creating a
GUI using tkinter is an easy task.

To create a tkinter app:

• Importing the module – tkinter

• Create the main window (container)
• Add any number of widgets to the main window
• Apply the event Trigger on the widgets.

Sample Code

import tkinter
from tkinter import *
#Create Chat window
ChatLog=Text(base,bd=0,bg="white”,height="8”,width="50", font="Arial",)
#Bind scrollbar to Chat window
Scrollbar=Scrollbar(base,command=ChatLog.yview,cursor="heart")
ChatLog['yscrollcommand'] = scrollbar.set
#Create Button to send message
SendButton=Button(base,font=("Verdana",12,'bold'),text="Send”,width="12
”,height=5,bd=0,bg="#32de97”,activebackground="#3c9d9b",fg='#ffffff',
command= send )

Dept of CSE, GMRIT Page 16

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



5.OUTPUT

Fig4: Output1

Fig5: Output2

Dept of CSE, GMRIT Page 17

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021

6. RESULTS & DISCUSSION

• There is no standard metric in finding the accuracy of the chatbot system.

• But, one can say accuracy of a chatbot can be defined as the percentage of utterances that had the
correct intent returned.

• We took more than 150 intents for this project, and the correct responses out of all the queries given
were ranged from 145 to 148.

• Therefore, the accuracy we got for this chat bot is 93.5%

Dept of CSE, GMRIT Page 18

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



7.SOURCE CODE

Ch_5.ipynb:
import nltk
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
import json
import pickle

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout
from keras.optimizers import SGD
import random

words=[]
classes = []
documents = []
ignore_words = ['?', '!']
data_file = open('intents.json').read()
intents = json.loads(data_file)

for intent in intents['intents']:

for pattern in intent['patterns']:

#tokenize each word

w = nltk.word_tokenize(pattern)
words.extend(w)

Dept of CSE, GMRIT Page 19

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



documents.append((w, intent['tag']))
# add to our classes list
if intent['tag'] not in classes:
classes.append(intent['tag'])

# lemmaztize and lower each word and remove duplicates

words = [lemmatizer.lemmatize(w.lower()) for w in words if w not in
ignore_words]
words = sorted(list(set(words)))
# sort classes
classes = sorted(list(set(classes)))
# documents = combination between patterns and intents
print (len(documents), "documents")
# classes = intents
print (len(classes), "classes", classes)
# words = all words, vocabulary
print (len(words), "unique lemmatized words", words)

pickle.dump(words,open('words.pkl','wb'))
pickle.dump(classes,open('classes.pkl','wb'))

# training data
training = []
# create an empty array for our output
output_empty = [0] * len(classes)

for doc in documents:

bag = []
pattern_words = doc[0]
Dept of CSE, GMRIT Page 20

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021

pattern_words = [lemmatizer.lemmatize(word.lower()) for word in

pattern_words]
for w in words:
bag.append(1) if w in pattern_words else bag.append(0)
output_row = list(output_empty)
output_row[classes.index(doc[1])] = 1

training.append([bag, output_row])
random.shuffle(training)
training = np.array(training)
# X - patterns, Y - intents
train_x = list(training[:,0])
train_y = list(training[:,1])
print("Training data created")

# model
model = Sequential()
model.add(Dense(128, input_shape=(len(train_x[0]),),
activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))# rectified linear unit
activation function
model.add(Dropout(0.5))
model.add(Dense(len(train_y[0]), activation='softmax'))

sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)

model.compile(loss='categorical_crossentropy', optimizer=sgd,
metrics=['accuracy'])

Dept of CSE, GMRIT Page 21

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021

#fitting and saving the model

hist = model.fit(np.array(train_x), np.array(train_y), epochs=200,
batch_size=5, verbose=1)
model.save('chatbot_model.h5', hist)
print("model created")

Ch_6.ipynb:
import nltk
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
import pickle
import numpy as np

from keras.models import load_model

model = load_model('chatbot_model.h5')
import json
import random
intents = json.loads(open('intents.json').read())
words = pickle.load(open('words.pkl','rb'))
classes = pickle.load(open('classes.pkl','rb'))

def clean_up_sentence(sentence):
sentence_words = nltk.word_tokenize(sentence)
sentence_words = [lemmatizer.lemmatize(word.lower()) for word in
sentence_words]
return sentence_words

Dept of CSE, GMRIT Page 22

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



def bow(sentence, words, show_details=True):
# tokenize the pattern
sentence_words = clean_up_sentence(sentence)
bag = [0]*len(words)
for s in sentence_words:
for i,w in enumerate(words):
if w == s:
bag[i] = 1
if show_details:
print ("found in bag: %s" % w)
return(np.array(bag))

def predict_class(sentence, model):

p = bow(sentence, words,show_details=False)
res = model.predict(np.array([p]))[0]
ERROR_THRESHOLD = 0.25
results = [[i,r] for i,r in enumerate(res) if r>ERROR_THRESHOLD]
results.sort(key=lambda x: x[1], reverse=True)
return_list = []
for r in results:
return_list.append({"intent": classes[r[0]], "probability":
str(r[1])})
return return_list

def getResponse(ints, intents_json):

tag = ints[0]['intent']
list_of_intents = intents_json['intents']
for i in list_of_intents:
if(i['tag']== tag):
Dept of CSE, GMRIT Page 23

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



result = random.choice(i['responses'])
break
return result
def chatbot_response(msg):
ints = predict_class(msg, model)
res = getResponse(ints, intents)
return res
#Creating GUI with tkinter
import tkinter
from tkinter import *

def send():
msg = EntryBox.get("1.0",'end-1c').strip()
EntryBox.delete("0.0",END)
if msg != '':
ChatLog.config(state=NORMAL)
ChatLog.insert(END, "You: " + msg + '\n\n')
ChatLog.config(foreground="#442265", font=("Verdana", 12 ))

res = chatbot_response(msg)
ChatLog.insert(END, "Bot: " + res + '\n\n')

ChatLog.config(state=DISABLED)
ChatLog.yview(END)

base = Tk()
base.title("Hello")
base.geometry("400x500")

Dept of CSE, GMRIT Page 24

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



base.resizable(width=FALSE, height=FALSE)

#Create Chat window

ChatLog = Text(base, bd=0, bg="white", height="8", width="50",
font="Arial",)
ChatLog.config(state=DISABLED)

#Bind scrollbar to Chat window

scrollbar = Scrollbar(base, command=ChatLog.yview, cursor="heart")
ChatLog['yscrollcommand'] = scrollbar.set

#Create Button to send message

SendButton = Button(base, font=("Verdana",12,'bold'), text="Send",
width="12", height=5,
bd=0, bg="#32de97",
activebackground="#3c9d9b",fg='#ffffff',
command= send )

#Create the box to enter message

EntryBox = Text(base, bd=0, bg="white",width="29", height="5",
font="Arial")

#Place all components on the screen

scrollbar.place(x=376,y=6, height=386)
ChatLog.place(x=6,y=6, height=386, width=370)
EntryBox.place(x=128, y=401, height=90, width=265)
SendButton.place(x=6, y=401, height=90)

base.mainloop()

Dept of CSE, GMRIT Page 25

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



8.CONCLUSION

From our perspective, chatbots or smart assistants with artificial intelligence are dramatically
changing businesses. There is a wide range of chatbot building platforms that are available for various
enterprises, such as e-commerce, retail, banking, leisure, travel, healthcare, and so on.

In his project the implemented BOT helps to the users to know the maximum information about
college related queries and provides a joyful environment to interact with the chatbot through text as a input
and provide text as a output. It tries to answer the maximum queries up to its knowledge.

Chatbots reach put to a large audience on massaging apps and be more effective than humans. They
may be develop into a capable information- gathering tool soon. Future work is text to speech conversation
and speech to text conversation and speech to speech conversation.

Dept of CSE, GMRIT Page 26

 COLLEGE WEBSITE CHATBOT – A BOT CAN CREATE A BOND 2021



9.REFERENCES

1. D. Carlander Reuterfelt, A. Carrera, C. A. Iglesias, O. Araque, J. F. Sánchez Rada and S. Muñoz,

"JAICOB: A Data Science Chatbot," in IEEE Access, vol. 8, pp., 2020.

2. G. Daniel, J. Cabot, L. Deruelle and M. Derras, "Xatkit: A Multimodal Low-Code Chatbot

Development Framework," in IEEE Access, vol. 8, pp., 2020.

3. Lei Cui, Shaohan Huang, Furu Wei, Chuanqi Tan, Chaoqun Duan, and Ming Zhou "SuperAgent: A
Customer Service Chatbot for E-commerce Websites", Association for Computational Linguistics,
2017.

4. E. H. Wu, C. Lin, Y. Ou, C. Liu, W. Wang and C. Chao, "Advantages and Constraints of a Hybrid
Model K-12 E-Learning Assistant Chatbot," in IEEE Access, vol. 8, pp., 2020.

5. Boris Galitsky, Dmitry Ilvovsky "Chatbot with a Discourse Structure-Driven Dialogue

Management", Association for Computational Linguistics, 2017.

6. L. Zhang, Y. Yang, J. Zhou, C. Chen and L. He, "Retrieval-Polished Response Generation for
Chatbot," in IEEE Access, vol. 8, pp., 2020.

7. Roland Kuhn ,Renato De Mori,"A Cache-Based Natural Language Model for Speech Recognition"
IEEE Transactions on pattern analysis and machine intelligence, IEEE.

8. Manjot Kaur, Lakhvir Garcha “Speaker Independent Isolated Word Speech to Text Conversion
Using Auto Spectral Subtraction for Punjabi Language”, International Journal of Scientific and
Research Publications, 2017.

Dept of CSE, GMRIT Page 27